Claude Opus 5 (xHigh): benchmark results
Provider: Anthropic. Released 2026-07-24. Access: API.
Aggregate Rating 1927 ± 11, rank #23 of 2168 rated models, from 147 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FutureSearch BTF-3 | 0.12 | Pooled Brier/RPS Score | 100 |
| FutureSearch BTF-3 Binary | 0.12 | Binary Brier Score | 100 |
| FutureSearch BTF-3 Numeric | 0.13 | Numeric RPS | 100 |
| GameCraft-Bench | 68.44 | Overall rubric score (%) | 100 |
| OckBench | 95 | Accuracy (%) | 100 |
| ProgramBench | 4.5 | Resolved (%) | 100 |
| ProgramBench Almost | 37 | Almost (%) | 100 |
| SWE Refactor Bench | 47 | Score (out of 100) | 100 |
| Conceptual Reasoning Index - Decision Theory (DTBench) | 96.45 | Chance-Corrected Score (0-100) | 99.1 |
| AA-Omniscience Index - Software Engineering (SWE) - Swift | 92 | Omniscience Index | 99 |
| Epoch AI - Dtbench | 97.87 | Score | 98.9 |
| Creative Writing (Lechmazur) | 3.73 | Mean Score | 98.3 |
Interactive version: theaggregate.ai/model?slug=claude-opus-5-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-20.